INDEX

Explanations

instances of the word "specific" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Adsorption

-0.52

 rowCount

-0.52

 Sleeping

-0.50

NameInMap

-0.50

chond

-0.48

 Pillow

-0.48

 setLoading

-0.48

 Sleep

-0.47

 Inflation

-0.47

strut

-0.47

POSITIVE LOGITS

 specific

1.09

specific

1.04

Specific

0.99

 SPECIFIC

0.98

 Specific

0.98

 specifics

0.89

 specifically

0.88

SPECIFIC

0.88

specifically

0.85

Specifically

0.84

Activations Density 0.120%

instances of the word "specific" and its variations

No Comments

No Known Activations